agentmods.dev

seoul-construction-mcp CLAUDE.md

seoul-construction-mcp CLAUDE.md is an instructions file for Claude Code from hlucent/seoul-construction-mcp. It costs 5,187 tokens per session, scanned A, original, MIT.

Project instructions for a Node.js MCP server that searches Seoul construction data from South Korea’s open-data service. MCP lets an AI assistant use the project’s data-search tools through a standard connection.

In plain words
What is it for?
For maintaining the server and using its four documented tools to search construction projects, filter district work, check progress, and retrieve project photos.
Why use it?
They give the coding agent project-specific facts, file locations, deployment details, and rules for communicating with a non-developer. This helps prevent work on outdated copies or the wrong entry file.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

not rated 0 changed yesterday A scan 5,187 tokens original MIT
View the source file hlucent/seoul-construction-mcp
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/hlucent/seoul-construction-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/hlucent/seoul-construction-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for seoul-construction-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hlucent/seoul-construction-mcp/claude-md.svg)](https://agentmods.dev/instructions/hlucent/seoul-construction-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/hlucent/seoul-construction-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/hlucent/seoul-construction-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 5,187 This file is loaded in full into every session.
When invoked 5,187 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.05187 $0.05187
Opus 5 $0.02593 $0.02593
Sonnet 5 $0.01037 $0.01037
Haiku 4.5 $0.00519 $0.00519

Measured yesterday against content hash 396f50e70f5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

seoul-construction-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — 서울시 건설알림이 MCP 프로젝트

프로젝트 개요

서울시 열린데이터광장의 건설공사 관련 데이터를 MCP(Model Context Protocol) 서버로 제공하는 프로젝트. Claude.ai에서 커넥터로 연결해 자연어로 서울시 공사 현황을 검색/조회할 수 있게 해준다.

  • 배포 주소: 없음 — fly.io 앱(seoul-construction-mcp)은 2026-09-03에 완전히 삭제됨. 현재는 로컬/각자 설치 방식으로만 운영 (README.md "설치 방법 → 1. 로컬 설치" 참고).
  • GitHub: hlucent/seoul-construction-mcp
  • 실제 작업 폴더(확정): C:\Users\hwang\Projects\seoul-construction-mcp (.git 존재, origin이 github.com/hlucent/seoul-construction-mcp로 연결됨, 최신 커밋과 코드가 일치하는 진짜 작업 폴더)
  • 실제 코드 진입점: src/index.js (Node.js 프로젝트. main.py 아님)
  • 참고: 과거 저장소명은 construction-alert-mcp, 작업 폴더는 C:\Users\hwang\project\construction-alert-mcp였으나 이후 seoul-construction-mcp로 개편됨. 앞으로 이 프로젝트 작업은 반드시 위 Projects 폴더에서만 진행할 것.
  • 사용자(청정)는 비개발자 — 모든 안내는 복사-붙여넣기 가능한 완성된 명령어로, 어느 창(PowerShell/메모장/브라우저)에 입력하는지 명확히 구분해서 제공할 것.

현재 제공 중인 도구 (4개)

  1. search_construction_projects — 사업개요 검색 (OA-15585), 자치구/키워드/도급액 필터
    • 발주처_연락처/건설사업관리단_연락처/시공사_연락처(TEL_1~3) 필드 포함
  2. search_construction_work_by_district — 자치구별 공사 정보 검색 (OA-1222)
  3. get_construction_progress — 공정률/기성률/D-Day 등 진행 현황. 공정률/대비율이 0이면 "미입력"으로 표시(formatRate 헬퍼). min_amount(도급액 기준) 클라이언트단 필터 지원. API 자체 필터는 없음.
  4. get_construction_project_photos — 사업코드(pjt_cd)로 현장 사진 목록 조회 (OA-15586)
    • 모든 사업에 사진이 있는 건 아님 (소규모/단기 사업은 사진 없는 경우 많음)
    • 대형 장기사업(예: 강남순환도시고속도로)은 주기적으로 사진 업데이트됨

아키텍처 핵심 사항

  • HTTP 기반 StreamableHTTPServerTransport 사용 (fly.dev 배포 필수 조건, stdio 아님)
  • 인증 방식(2026-08-24 재도입): 쿼리 파라미터 ?key=를 MCP_ACCESS_KEY(서버 전용 접근 비밀키)와 timingSafeEqual로 비교. 키 없거나 틀리면 401로 강제 거부. rate limit 미들웨어보다 먼저 실행되어, 인증 실패 요청은 rate limit 카운터를 소모하지 않는다. (과거 2026-08-16 커밋 d29cc50에서 사용 편의성을 위해 ?key= 인증을 한 번 제거했었으나, 2026-08-24에 "타인 접속 완전 차단"이 목표로 바뀌며 다시 추가함. 이번엔 "사용자가 자기 서울API키를 제공"하는 방식이 아니라 "서버가 전용 비밀키를 자체 보유하고 대조"하는 방식으로 설계가 다름.)
  • SEOUL_OPENAPI_KEY(서울시 업스트림 API 호출용)와 MCP_ACCESS_KEY(이 서버 자체 접근용)는 서로 다른 목적의 별개 키. 둘 다 fly secrets로 서버가 보유.
  • CDATA XML 파싱 이슈 수정 완료
  • fly.toml: 앱 이름은 2026-08-24부터 GitHub에 커밋하지 않음(.gitignore 처리) — 저장소명만으로 실제 fly.io 앱 주소를 유추할 수 없게 하기 위함. 로컬 fly.toml에서 실제 값 확인. internal_port 8080, auto_stop/start_machines 켜짐
  • Dockerfile: node:20-slim → npm ci --omit=dev → node src/index.js 실행
  • 로컬 .env는 테스트 전용 (SEOUL_OPENAPI_KEY, MCP_ACCESS_KEY 둘 다 필요)

Read the full file on GitHub · 278 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday Changed · +1 lines · +9 tokens per session 396f50e70f5d
  2. 5d ago First seen · 277 lines · 5,178 tokens per session scan A 0ccc4745dc25

Subscribe to this mod's changes

seoul-construction-mcp CLAUDE.md is an instructions file published in the GitHub repository hlucent/seoul-construction-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 5,187 tokens to every session, about $0.0259 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Research
Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens